Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD CLEMSON UNIVERSITY CLEMSON, SC USA ABSTRACT Strength Image Computation: A strength image indicates the probability of each pixel belonging to the target: EXPERIMENTAL RESULTS We present an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature-spatial space, with each ellipsoid corresponding to a different fragment. The fragments are automatically adapted to the image data, being selected by an efficient region-growing procedure and updated according to a weighted average of the past and present image statistics. Modeling of target and background are performed in a Chan-Vese manner, using the framework of level sets to preserve accurate boundaries of the target. The extracted target boundaries are used to learn the dynamic shape of the target over time, enabling tracking to continue under total occlusion. Experimental results on a number of challenging sequences demonstrate the effectiveness of the technique. ours Level Set Formulation: The energy functional over the implicit function is single Gaussian TRACKING FRAMEWORK Bayesian Formulation: The probability of the contour at time t given the previous contours and all the measurements is formulated using Bayes’ rule: individual fragments linear classifier length of curve Solution iterates: SEGMENTATION pixels inside contour pixels outside contour Fragment Modeling: Assuming conditional independence among the pixels, the joint probability of the pixels in a region is given by: Region growing algorithm repeatedly accumulates pixels within t standard deviations of the Gaussian model of the fragment; automatically computes the number of fragments. Results of the algorithm on various sequences Occlusion: is detected by the rate of decrease in the object size over the past few frames; is handled by searching over the learned database to find the contour that most closely matches the one just prior to occlusion using Hausdorff distance. Hallucinated contours are indicated by . image foreground fragments where y is the feature vector of a pixel containing its spatial coordinates and color measurements. The likelihood of the individual pixel is given by the Gaussian mixture model (GMM): CONCLUSION Non-rigid tracking algorithm is based upon modeling the foreground and background regions with a mixture of Gaussians. A simple and efficient region-growing procedure initializes the models. The strength image computed using the GMM is embedded into a level set framework to extract contours. Joint feature tracking and model updating are both incorporated to improve performance. foreground ellipsoids background fragments where is the probability that the pixel was drawn from the jth fragment, k* is the number of fragments in the target or background, is the mean and is the covariance of the jth fragment FRAGMENT UPDATE The spatial parameters of the fragment are updated by averaging the motion vectors obtained for feature points in a fragment using a Joint Lucas-Kanade approach. The appearance parameters are updated using the past and present image statistics: